Towards Deep Active Learning in Avian Bioacoustics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rauch, Lukas, Huseljic, Denis, Wirth, Moritz, Decke, Jens, Sick, Bernhard, Scholz, Christoph
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910684537683968
author Rauch, Lukas
Huseljic, Denis
Wirth, Moritz
Decke, Jens
Sick, Bernhard
Scholz, Christoph
author_facet Rauch, Lukas
Huseljic, Denis
Wirth, Moritz
Decke, Jens
Sick, Bernhard
Scholz, Christoph
contents Passive acoustic monitoring (PAM) in avian bioacoustics enables cost-effective and extensive data collection with minimal disruption to natural habitats. Despite advancements in computational avian bioacoustics, deep learning models continue to encounter challenges in adapting to diverse environments in practical PAM scenarios. This is primarily due to the scarcity of annotations, which requires labor-intensive efforts from human experts. Active learning (AL) reduces annotation cost and speed ups adaption to diverse scenarios by querying the most informative instances for labeling. This paper outlines a deep AL approach, introduces key challenges, and conducts a small-scale pilot study.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Deep Active Learning in Avian Bioacoustics
Rauch, Lukas
Huseljic, Denis
Wirth, Moritz
Decke, Jens
Sick, Bernhard
Scholz, Christoph
Sound
Artificial Intelligence
Audio and Speech Processing
Passive acoustic monitoring (PAM) in avian bioacoustics enables cost-effective and extensive data collection with minimal disruption to natural habitats. Despite advancements in computational avian bioacoustics, deep learning models continue to encounter challenges in adapting to diverse environments in practical PAM scenarios. This is primarily due to the scarcity of annotations, which requires labor-intensive efforts from human experts. Active learning (AL) reduces annotation cost and speed ups adaption to diverse scenarios by querying the most informative instances for labeling. This paper outlines a deep AL approach, introduces key challenges, and conducts a small-scale pilot study.
title Towards Deep Active Learning in Avian Bioacoustics
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2406.18621